Skripsi

ANALISIS KINERJA METODE K-NEAREST NEIGHBORS UNTUK PENGEMBANGAN SISTEM OTOMASI KLASIFIKASI SAMPAH KERTAS SECARA REAL-TIME

---

The increasing volume of paper waste necessitates the development of more effective and efficient sorting systems to support recycling processes and reduce environmental impacts. Manual paper waste sorting is considered less optimal due to its time-consuming nature and susceptibility to human error. Therefore, this study aims to analyze the performance of the K-Nearest Neighbors (KNN) method in developing a real-time automated paper waste classification system based on digital image processing. The system was developed as a prototype consisting of a belt conveyor as the object transport medium, web camera for image acquisition, and mini computer as the data processing unit. The classification process begins with real-time image acquisition, followed by pre-processing to enhance image quality, color feature extraction using the HSV color space, and shape feature extraction based on contour features, namely area and perimeter. The dataset used in this study consists of 300 images representing three types of paper: Buffalo Paperboard, Art Paper, and HVS. The data were divided into 70% training data and 30% testing data to objectively evaluate system performance. The KNN was implemented using Euclidean distance with various values of k to determine optimal parameter. Experimental results indicate that value of k = 3 yields the best performance with an accuracy of 85%. These findings demonstrate that the KNN method can be effectively applied in an automated paper waste classification system and has the potential to be further developed as an initial solution for intelligent waste sorting systems based on image processing and machine learning technologies.

---

Availability

Detail Information

Series Title

-

Call Number

T1915822025

Publisher

Indralaya : Prodi Magister Teknik Mesin, Fakultas Teknik Universitas Sriwijaya., 2025

Collation

iii, 100 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Magister Teknik Mesin
Pembelajaran Mes

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment